AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FedCDWA: Decoupled Federated Prototype Distillation with Hierarchical Wasserstein Aggregation

Zhenshen Liu, Kai Fan, Wenjie Li, Kuan Zhang, HUI LI, Yintang Yang

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use FedCDWA instead of FedProtofederated prototype learning · SVHN (10 clients)Local accuracy: 85.92 -> 87.56Improved
use FedCDWA instead of FedAvgfederated learning · CIFAR-10 (10 clients)Local accuracy: 50.75 -> 61.25Improved
use FedCDWA instead of FedGMKDfederated prototype distillation · CIFAR-100 (10 clients)Global accuracy: 16.26 -> 18.01Improved
fewer clients (stronger heterogeneity) with FedCDWAFedCDWA · CIFAR-100Local accuracy gain over FedGMKD: +4.11% at 10 clients vs +1.06% at 50 clientsImproved
FedCDWA vs FedHKD on CIFAR-10 global accuracy at 10 clientsFedCDWA · CIFAR-10 (10 clients)Global accuracy: 49.73 -> 51.38Improved
FedCDWA vs FedProx local accuracy at 50 clientsFedCDWA · CIFAR-10 (50 clients)Local accuracy: 67.49 -> 67.74Improved
FedCDWA adds computational overhead compared with FedAvgFedCDWA · CIFAR-10Per-round time per client (s): 2.67 -> 3.35Hurt
FedCDWA vs FedAvg time on SVHNFedCDWA · SVHNPer-round time per client (s): 2.49 -> 2.49No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy